Dynamic Symbol Library for Degraded Mark Reading
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for automatically identifying marked symbols on animals are unreliable due to degradation over time, requiring simple codes or suffering from both weaknesses.
Innovation Solution
The use of one or more reference shapes for comparison, with a symbol library that is continually updated with the most recently read shape after validation, minimizing the number of reference symbols and customizing for individual use, while averaging multiple reads and allowing 'backing up' to prior reference shapes to handle temporary changes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional symbol recognition methods are used, then the system is simple to operate, but the reliability of reading symbols degrades over time due to marking degradation
Solution Approach 1:
The symbol library is dynamically updated over time by incorporating newly recognized symbols and their variations. The system adapts to degradation patterns by continuously learning from observed markings, transforming a static recognition system into a dynamic one that improves reliability without requiring complex manual intervention
Solution Approach 2:
The system performs self-updating by automatically incorporating newly read symbols into the reference library without external intervention. This self-service mechanism allows the system to adapt to degradation patterns autonomously, maintaining high reliability while keeping the operational complexity low
2Adaptability or versatility
If a fixed symbol library is used, then the device complexity is low, but the adaptability to individual uses and degradation patterns is poor
Solution Approach 1:
The symbol library automatically updates itself by incorporating newly recognized symbols and their degradation variations. This self-service approach enables customization for individual uses without requiring complex manual library management, as the system adapts autonomously to specific applications and degradation patterns
Solution Approach 2:
The system changes the parameters of symbols in the library over time by incorporating observed variations and degradation patterns. This allows the library to adapt to individual uses and specific degradation characteristics without requiring complex manual reconfiguration
Data Source
AI summary
A method of reading degraded symbols is described. A symbol has an initial shape, which is marked on an object. Marks, shapes, symbols, and object ID are managed separately. A symbol library with symbols and associated shapes is initially created. Shapes in the library are updated from shapes of marks as the marks degrade over time. A read mark is compared to all the shapes in the library to determine a most likely shape. A selection set is used to limit symbol selection, based on the comparison, to valid symbols. The symbol library and selection set may be customized to each usage of the method. Comparison methods use probability distributions. Confidence values are used to validate output, generate warnings, and to control updating of the library. Weighted averaging may be used at the level of shapes, comparison distributions, or selections. One application is reading tattooed marks on rodent tails in a vivarium.